Computer Rating System Prediction Results for College Football (NCAA IA)

2014 Season Totals

Through 2014-09-14
Rank System Pct. Correct Against Spread Absolute Error Bias Mean Square Error games suw sul atsw atsl
1Dunkel Index0.820900.5789513.12960.6687286.441134110247756
2Brent Craig 20.812500.5052612.46084.5719248.6459678184847
3Sagarin Predictor0.805970.4812013.36781.0649295.284134108266469
4Nutshell Girl0.802080.4631613.67602.2531284.8379677194451
5Dokter Entropy0.798510.4621213.13710.9196272.461134107276171
6Pigskin Index0.798510.4609413.47750.1493288.582134107275969
7Sagarin Elo Score0.798510.4511314.33840.2128322.501134107276073
8Billingsley+0.791040.5338313.8196-0.8377314.042134106287162
9Pi-Rate Ratings0.791040.5263213.71031.0046304.267134106287063
10Directorofinformation0.791040.5188013.16900.2169282.883134106286964
11Thompson Average0.791040.4736813.12200.4608277.108134106286370
12Thompson CAL0.791040.5112812.80750.5716262.505134106286865
13Line (updated)0.791040.4381012.67910.5224256.104134106284659
14Billingsley0.783580.5112814.4397-1.2231335.410134105296865
15ARGH Power Ratings0.783580.4496114.3993-0.1007319.450134105295871
16CPA Retro0.783580.4661714.03461.4757311.877134105296271
17CPA Rankings0.783580.4812013.94810.9896298.513134105296469
18Pi-Ratings Mean0.783580.5833313.1202-0.1768276.331134105297755
19Computer Adjusted Line0.783580.4464312.73880.4776257.840134105295062
20Thompson ATS0.783580.5413512.6381-0.5515255.341134105297261
21Catherwood Ratings0.776120.4418614.75370.1716350.619134104305772
22Keeper0.776120.4511314.59900.4704332.359134104306073
23Sagarin0.776120.3985014.05460.7901307.515134104305380
24Massey Consensus0.776120.4511313.77980.1786301.130134104306073
25Massey Ratings0.776120.4480013.66420.5149296.246134104305669
26Line (midweek)0.7761212.81340.5672263.61213410430
27System Median0.776120.4496113.44710.3469284.152134104305871
28System Average0.776120.4469713.46110.1232286.667134104305973
29PI-Rate Bias0.776120.5343513.48280.7604293.976134104307061
30The Power Rank0.768660.5263213.1940-0.0763297.075134103317063
31Payne Power Ratings0.768660.4511314.15460.2028314.723134103316073
32DP Dwiggins0.768660.4573614.9030-0.0522348.425134103315970
33Edward Kambour0.763780.4603214.25450.4471318.30712797305868
34MDS Model0.761190.4962415.2400-0.9351370.266134102326667
35Sagarin Golden Mean0.761190.4736814.38210.2979326.945134102326370
36Howell0.761190.5581414.1793-0.3506334.277134102327257
37Brent Craig0.761190.3985013.90441.1832291.930134102325380
38Fremeau FEI0.761190.5118113.78360.2313303.828134102326562
39Line (opening)0.761190.5377412.81340.6642263.045134102325749
40Atomic Football0.761190.4285713.31770.6550273.820134102325776
41Ashby AccuRatings0.761190.4603213.4626-0.2686285.133134102325868
42Compughter Ratings0.761190.4812013.63270.2381297.299134102326469
43Laz Index0.761190.5263213.6444-1.1983302.823134102327063
44Lee Burdorf0.759400.4545515.0126-0.9964346.427133101326072
45Moore Power Ratings0.755730.3923114.95921.0510345.23613199325179
46Stat Fox0.753730.4218814.19401.1494325.134134101335474
47Cleanup Hitter0.750000.4842115.54483.9073406.8609672244649
48Donchess Inference0.750000.4732814.7181-1.0725344.90613299336269
49Sportrends0.747830.5225215.4610-1.8347403.58711586295853
50Laffaye RWP0.746270.5037615.6040-2.7040390.764134100346766
51Beck Elo0.746270.3909815.0849-0.6112350.413134100345281
52Randal Horobik0.746270.4062515.46270.3955346.022134100345276
53Laffaye XWP0.738810.4436115.98582.8739416.55113499355974
54Regression-Based Analys0.738810.4140615.21642.2910352.14213499355375
55Super List0.738810.5681815.10900.4061363.65713499357557
56Marsee0.731340.4436115.72390.0970381.84313498365974
57Born Power Index0.723880.4060215.42880.4824360.73213497375479
58PerformanZ Ratings0.716420.4812015.2431-1.0921377.43913496386469
59Daniel Curry Index0.716420.4166716.5404-0.5089424.09513496385577
60Dave Congrove0.708960.4360915.2462-0.6371378.07313495395875
61NutShell Sports0.696970.4883715.7858-0.6116390.60213292406366
62Tempo Free Gridiron0.694030.5000015.3731-2.0746378.35813493416666
63Covers.com0.671640.5038815.2018-1.2213365.87313490446564
64Stephen Kerns0.664120.4418616.2153-2.3418392.60713187445772

* This system does not make predictions.  I make predictions for this
  system by translating it to a new scale that allows for making predictions.



Retrodictive records are found by taking the ratings from the current week
and applying them to the entire season to date.

The ideal system would be one that has the highest correct game decisions,
has the smallest mean error(deviation from the actual game result), and has
a bias of zero.

Mean Error = average[abs(prediction-actual)]

      Bias = agerage(prediction - actual)

      Std. = Standard Deviation of individual game biases